Charlie — Case Study

Designing Trust Into a Conversational AI

A privacy layer between the user and the model, built to feel invisible, not enforced.

RoleDesign Engineer

TimelineMar 2026 – June 2026

WithEngineers, PM, Growth Officer

NDA Alert — mockups in this case study are illustrative, reimagined to protect sensitive product details while preserving the design approach, decisions, and outcomes that shaped the work.

01Context

A Privacy Layer, Not a Chat Feature

Charlie sits between user and model, masking identity before any query leaves the product.

Charlie is an AI-powered personal assistant that masks identifying data before a query leaves the product, so the model gets useful context without knowing who the user is. The first wedge was personal finance, where trust breaks quickly if security feels confusing or heavy.

I led user research, feature design, and rapid AI-assisted prototyping across onboarding, data masking, source ingestion, and recurring assistant tasks.

Diagram showing the gap between enterprise buyer needs and end-user trust needs.

Fig: The gap between buyer requirements and end-user trust

02Problem

Make Privacy Feel Invisible

Every security step is a moment where trust either grows — or quietly breaks.

Users want deeply personalized financial answers, but the product has to handle sensitive data to get there. Every security step is a moment where confidence can grow, or trust can break.

The design challenge was making that infrastructure legible without making it feel like surveillance. Users needed clarity, control, and momentum inside the same flow.

Illustrative Charlie onboarding screens for a privacy-first assistant.

Fig: Onboarding designed to build trust before asking for deeper context

Charlie masking user data before sending a query to an external LLM.

Fig: Charlie disguising user data before sending it to an LLM

03Discovery

Not Waiting for a Brief

Proactive research surfaced four strategy questions leadership could use to shape the roadmap.

I ran proactive unmoderated sessions to pressure-test early interaction patterns and understand where security friction made users hesitate. The work quickly moved beyond screens into product strategy: who is this actually for, and what does each audience need to trust?

In a B2B2C model, the enterprise buyer and the end user are different people. I translated session observations into four strategy questions that leadership could use to shape the roadmap.

Research observations translated into product strategy questions.

Fig: Observations turned into strategic product questions

04Design & Architecture

Features That Answered Real Questions

I moved fast by treating AI as a design-to-code partner - going from feature brief to functional prototype in 1-2 days. My focus was 4 modular pillars, each designed so privacy operates as invisible infrastructure:

1. Visualizing the Knowledge Graph: Translating a growing network of connected financial sources into an interface users can understand, manage, and audit at a glance.

Interactive knowledge graph interface for Charlie, illustrating connected financial nodes.

Fig: Interactive knowledge graph - Illustrative only; original data and structure withheld under NDA

Income and Spending panel showing a mortgage balance field sourced from MonthlySavings.pdf.

Fig: Different information sourced from user's: documents, chatting with Charlie, bank acc.

2. Frictionless Ingestion via Email Sync: A secure email-forwarding verification pipeline - frictionless enough that connecting a new source feels like a natural step, not a security checkpoint.

Document inbox with email verification flow for connecting a new data source.

Fig: A way to connect through emails seamlessly

3. Local-First Voice Architecture: Protected sensitive user input while preserving the speed and naturalness of voice interaction.

Early ideation concept for Charlie's local-first voice architecture.

Fig: Exploring the voice interaction concept

4. Autonomous Task Execution: A structured task-scheduling modal that lets users set up persistent financial check-ins in plain English - no configuration overhead.

Create a routine modal for scheduling a recurring financial check-in task.

Fig: Tasks to run on recurrence

05Testing

One Thread, Four Sessions

Moderated testing on the Data Package Review step shaped the v2 direction for consent and trust.

I ran moderated evaluation sessions across mobile and desktop, focused on the Data Package Review component: the moment where users decide what context to share before a query goes out.

The sessions surfaced friction around masking and review, which directly informed the v2 direction for clearer consent, better defaults, and less cognitive load at the point of sharing.

Brief insights from Charlie user testing sessions.

Fig: Brief insights from testing

06Impact

Built to Scale Trust

Research and prototypes shaped the roadmap, the testing strategy, and the story told to institutional stakeholders.

The research, prototypes, and interaction framework did not just produce screens. They fed into the product roadmap, the formal testing strategy, and the enterprise narrative presented to institutional stakeholders.

Charlie is being positioned for a closed-to-institutional launch, and the design system I established gives the team a foundation to keep scaling privacy-first AI workflows.

Next Case Study Solving Fragmented Lease Workflows: Designing a Unified System & Intelligent (NLP) Assistant, Clara Read →